Matches in SemOpenAlex for { <https://semopenalex.org/work/W1486649854> ?p ?o ?g. }
- W1486649854 endingPage "3302" @default.
- W1486649854 startingPage "3294" @default.
- W1486649854 abstract "We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage. Sentences that share semantic and syntactic properties are thus mapped to similar vector representations. We next introduce a simple vocabulary expansion method to encode words that were not seen as part of training, allowing us to expand our vocabulary to a million words. After training our model, we extract and evaluate our vectors with linear models on 8 tasks: semantic relatedness, paraphrase detection, image-sentence ranking, question-type classification and 4 benchmark sentiment and subjectivity datasets. The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice." @default.
- W1486649854 created "2016-06-24" @default.
- W1486649854 creator A5000111344 @default.
- W1486649854 creator A5006455453 @default.
- W1486649854 creator A5055166817 @default.
- W1486649854 creator A5058557954 @default.
- W1486649854 creator A5070642269 @default.
- W1486649854 creator A5071983998 @default.
- W1486649854 creator A5085020955 @default.
- W1486649854 date "2015-12-07" @default.
- W1486649854 modified "2023-10-18" @default.
- W1486649854 title "Skip-thought vectors" @default.
- W1486649854 cites W1493309689 @default.
- W1486649854 cites W1566289585 @default.
- W1486649854 cites W1614298861 @default.
- W1486649854 cites W1681397005 @default.
- W1486649854 cites W1753482797 @default.
- W1486649854 cites W1832693441 @default.
- W1486649854 cites W1861492603 @default.
- W1486649854 cites W1905882502 @default.
- W1486649854 cites W1924770834 @default.
- W1486649854 cites W1957706851 @default.
- W1486649854 cites W1980776243 @default.
- W1486649854 cites W2064675550 @default.
- W1486649854 cites W2099884836 @default.
- W1486649854 cites W2103305545 @default.
- W1486649854 cites W2106612368 @default.
- W1486649854 cites W2120615054 @default.
- W1486649854 cites W2126725946 @default.
- W1486649854 cites W2130942839 @default.
- W1486649854 cites W2131744502 @default.
- W1486649854 cites W2149557440 @default.
- W1486649854 cites W2154359981 @default.
- W1486649854 cites W2155484602 @default.
- W1486649854 cites W2157331557 @default.
- W1486649854 cites W2172140247 @default.
- W1486649854 cites W2187089797 @default.
- W1486649854 cites W2250305120 @default.
- W1486649854 cites W2250307601 @default.
- W1486649854 cites W2250565861 @default.
- W1486649854 cites W2251869843 @default.
- W1486649854 cites W2251919380 @default.
- W1486649854 cites W2251939518 @default.
- W1486649854 cites W2787381839 @default.
- W1486649854 cites W2962706528 @default.
- W1486649854 cites W2962835968 @default.
- W1486649854 cites W2963355447 @default.
- W1486649854 cites W2963504252 @default.
- W1486649854 cites W2964121744 @default.
- W1486649854 cites W2964308564 @default.
- W1486649854 hasPublicationYear "2015" @default.
- W1486649854 type Work @default.
- W1486649854 sameAs 1486649854 @default.
- W1486649854 citedByCount "620" @default.
- W1486649854 countsByYear W14866498542015 @default.
- W1486649854 countsByYear W14866498542016 @default.
- W1486649854 countsByYear W14866498542017 @default.
- W1486649854 countsByYear W14866498542018 @default.
- W1486649854 countsByYear W14866498542019 @default.
- W1486649854 countsByYear W14866498542020 @default.
- W1486649854 countsByYear W14866498542021 @default.
- W1486649854 countsByYear W14866498542022 @default.
- W1486649854 crossrefType "proceedings-article" @default.
- W1486649854 hasAuthorship W1486649854A5000111344 @default.
- W1486649854 hasAuthorship W1486649854A5006455453 @default.
- W1486649854 hasAuthorship W1486649854A5055166817 @default.
- W1486649854 hasAuthorship W1486649854A5058557954 @default.
- W1486649854 hasAuthorship W1486649854A5070642269 @default.
- W1486649854 hasAuthorship W1486649854A5071983998 @default.
- W1486649854 hasAuthorship W1486649854A5085020955 @default.
- W1486649854 hasConcept C104317684 @default.
- W1486649854 hasConcept C111919701 @default.
- W1486649854 hasConcept C118505674 @default.
- W1486649854 hasConcept C13280743 @default.
- W1486649854 hasConcept C138885662 @default.
- W1486649854 hasConcept C154945302 @default.
- W1486649854 hasConcept C185592680 @default.
- W1486649854 hasConcept C185798385 @default.
- W1486649854 hasConcept C189430467 @default.
- W1486649854 hasConcept C204321447 @default.
- W1486649854 hasConcept C205649164 @default.
- W1486649854 hasConcept C2777530160 @default.
- W1486649854 hasConcept C2777601683 @default.
- W1486649854 hasConcept C2780922921 @default.
- W1486649854 hasConcept C28490314 @default.
- W1486649854 hasConcept C41008148 @default.
- W1486649854 hasConcept C41895202 @default.
- W1486649854 hasConcept C55493867 @default.
- W1486649854 hasConcept C66746571 @default.
- W1486649854 hasConceptScore W1486649854C104317684 @default.
- W1486649854 hasConceptScore W1486649854C111919701 @default.
- W1486649854 hasConceptScore W1486649854C118505674 @default.
- W1486649854 hasConceptScore W1486649854C13280743 @default.
- W1486649854 hasConceptScore W1486649854C138885662 @default.
- W1486649854 hasConceptScore W1486649854C154945302 @default.
- W1486649854 hasConceptScore W1486649854C185592680 @default.
- W1486649854 hasConceptScore W1486649854C185798385 @default.
- W1486649854 hasConceptScore W1486649854C189430467 @default.